Developed by UZH researchers, the algorithm DroNet allows drones to fly completely by themselves through the streets of a city and in indoor environments. Therefore, the algorithm had to learn traffic rules and adapt training examples from cyclists and car drivers.
All today’s commercial drones use GPS, which works fine above building roofs and in high altitudes. But what, when the drones have to navigate autonomously at low altitude among tall buildings or in the dense, unstructured city streets with cars, cyclists or pedestrians suddenly crossing their way? Until now, commercial drones are not able to quickly react to such unforeseen events.
Integrate autonomously navigating drones
Researchers of the University of Zurich and the National Centre of Competence in Research NCCR Robotics developed DroNet, an algorithm that can safely drive a drone through the streets of a city. Designed as a fast 8-layers residual network, it produces two outputs for each single input image: a steering angle to keep the drone navigating while avoiding obstacles, and a collision probability to let the drone recognise dangerous situations and promptly react to them. “DroNet recognises static and dynamic obstacles and can slow down to avoid crashing into them. With this algorithm we have taken a step forward towards integrating autonomously navigating drones into our everyday life”, says Davide Scaramuzza, Professor for Robotics and Perception at the University of Zurich.
Powerful artificial intelligence algorithm
Instead of relying on sophisticated sensors, the drone developed by Swiss researchers uses a normal camera like that of every smartphone, and a very powerful artificial intelligence algorithm to interpret the scene it observes and react accordingly. The algorithm consists of a so-called Deep Neural Network. “This is a computer algorithm that learns to solve complex tasks from a set of ‘training examples’ that show the drone how to do certain things and cope with some difficult situations, much like children learn from their parents or teachers”, says Prof. Scaramuzza.
Cars and bicycles are the drones’ teachers
One of the most difficult challenges in Deep Learning is to collect several thousand ‘training examples’. To gain enough data to train their algorithms, Prof. Scaramuzza and his team collected data from cars and bicycles, that were driving in urban environments. By imitating them, the drone automatically learned to respect the safety rules, such as “How to follow the street without crossing into the oncoming lane”, and “How to stop when obstacles like pedestrians, construction works, or other vehicles, block their ways”. Even more interestingly, the researchers showed that their drones learned to not only navigate through city streets, but also in completely different environments, where they were never taught to do so. Indeed, the drones learned to fly autonomously in indoor environments, such as parking lots and office’s corridors.
Toward fully autonomous drones
This research opens potential for monitoring and surveillance or parcel delivery in cluttered city streets as well as rescue operations in disaster urban areas. Nevertheless, the research team warns from exaggerated expectations of what lightweight, cheap drones can do. “Many technological issues must still be overcome before the most ambitious applications can become reality,” says PhD student Antonio Loquercio.
Learn more: Drones learn to navigate autonomously by imitating cars and bicycles
The Latest on: Automated drones
[google_news title=”” keyword=”Automated drones” num_posts=”10″ blurb_length=”0″ show_thumb=”left”]
via Google News
The Latest on: Automated drones
- The FAR Part 5 Final Rule: A New Era for Drone Safety and Complianceon May 12, 2024 at 5:20 am
Enhancing Drone Safety and Compliance by DRONELIFE Contributing Editor Paul Rossi Stay tuned for the upcoming Weekly Wings Podcast, a discussion of trends and tech ...
- How Can Ukrainian Drones Keep Dropping Grenades Into Open Tank Hatches?on May 10, 2024 at 5:57 am
Videos show drones dropping grenades through the open hatches of abandoned Russian tanks to destroy them. So why don't Russian tankers just close the hatch?
- DJI Mini 4K review – Is this finally a no-compromise beginner's drone?on May 9, 2024 at 7:40 am
At the time of review, at launch, the DJI Mini 4K is retailing for $299 / £269 with one battery and controller, or $449 / £399 in the 'Fly More Combo' which includes a bag, charging hub, and total of ...
- Ondas Holdings' Airobotics and HHLA Sky Partner to Offer Drone Services for Terminal Operations and Critical Infrastructure in Germanyon May 9, 2024 at 5:35 am
Airobotics Ltd., a wholly-owned subsidiary of Ondas Holdings Inc., a leading provider of wireless networks and autonomous drones and automated data solutions, and HHLA Sky GmbH, a subsidiary ...
- This New Deadly Kamikaze Drone Can Reach 400 KPHon May 8, 2024 at 9:00 pm
EOS Technologie recently unveiled its newest ‘kamikaze’ drone that can reach speeds of up to 400 kph. Called the Veloce 330, this medium-range remotely operated munition was commissioned by France’s ...
- Ruko Veeniix V11 drone reviewon May 8, 2024 at 5:00 pm
The beginner drone market is one of the toughest ... The camera is completely automatic so shooting is very much a point-and-shot affair. It's a shame that basic control isn't available, but ...
- Ondas Holdings' Airobotics and HHLA Sky Partner to Offer Drone Services for Terminal Operations and Critical Infrastructure in Germanyon May 8, 2024 at 1:30 am
The Autonomous Drone Platforms are highly automated, AI-powered drone systems capable of continuous, remote operation and are marketed as "drone-in-a-box" turnkey data solution services.
- Stellar Blade: Best Drone Upgrades To Unlock ASAPon May 8, 2024 at 12:10 am
Eve's drone in Stellar Blade has a variety of functions that can make a big difference in the game. These upgrades, however, should be prioritized.
- Watch an exploding Ukrainian drone boat dodge fire from the air to kill one of the small, high-speed Russian ships still fighting in the Black Seaon May 6, 2024 at 9:27 am
Ukraine's military intelligence agency said its forces used Magura V5 naval drones to destroy a Russian military speedboat in Crimea.
via Bing News